Combining Siamese Network and Regression Network for Visual Tracking
Yao Ge, Rui Chen, Ying Tong, Xuehong Cao, Ruiyu Liang · IEICE Transactions on Information and Systems · 2020
We combine the siamese network and the recurrent regression network, proposing a two-stage tracking framework termed as SiamReg. Our method solves the problem that the classic siamese network can not judge the target size precisely and simplifies the procedures of regression in the training and testing process. We perform experiments on three challenging tracking datasets: VOT2016, OTB100, and VOT2018. The results indicate that, after offline trained, SiamReg can obtain a higher expected average overlap measure.